1 Setup

1.1 Loading libraries

library(tidyverse)
library(here)
library(readr)
library(data.table)

1.2 Loading in cleaned data

rwa <- "clean_data/rwa_clean.csv" %>%
    here() %>%
    read_csv()

2 Data

2.1 Raw

"raw_data/rwa.csv" %>%
    here() %>%
    read_csv() %>% 
    data.table()

2.2 Clean data

rwa %>% 
    data.table()

3 Questions

3.1 What’s the average RWA score for each gender?

rwa %>%
  group_by(gender) %>%
  summarise(mean_rwa = mean(rwa))
## `summarise()` ungrouping output (override with `.groups` argument)

3.2 What’s the average RWA score for left handed people vs. right handed people.

rwa %>%
  group_by(hand) %>%
  summarise(mean_rwa = mean(rwa))
## `summarise()` ungrouping output (override with `.groups` argument)

3.3 What’s the average family size for each type of childhood?

rwa %>%
  group_by(childhood) %>%
  summarise(mean_family_size = mean(family_size))
## `summarise()` ungrouping output (override with `.groups` argument)

3.4 What’s the average time to take the test for each education level?

rwa %>%
  group_by(education) %>%
  summarise(mean_test_time = mean(test_time))
## `summarise()` ungrouping output (override with `.groups` argument)

3.5 Whats the average RWA score for people aged

  • Under 18
  • 18 to 25
  • 26 to 40
  • 41 to 60
  • Over 60
rwa %>%
  mutate(
    age_group = case_when(
      age < 18 ~ "Under 18",
      age < 26 ~ "18 to 25",
      age < 41 ~ "26 to 40",
      age < 61 ~ "41 to 60",
      age > 60 ~ "Over 60"
    )
  ) %>%
  group_by(age_group) %>%
  summarise(
    mean_rwa = mean(rwa)
  )
## `summarise()` ungrouping output (override with `.groups` argument)